AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Xinyue Li, Dongyang Liu, Xiangyang Zhu, Will Beddow, Erwann Millon and 8 more

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 82 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale training data from 20M to 200M samplesLumina-Next · DPGDPG overall: 75.66 -> 85.80Improved
add high-quality tuning stage after high-res stage (ablation)Lumina-Image 2.0 · DPGDPG overall: 85.7 -> 86.6Improved
add high-quality tuning stage after high-res stage (ablation)Lumina-Image 2.0 · GenEvalGenEval overall: 0.67 -> 0.71Improved
train high-quality tuning from 5K to 11K steps (ablation)Lumina-Image 2.0 · DPGDPG overall: 87.2 -> 87.6Improved
train high-quality tuning from 5K to 11K steps (ablation)Lumina-Image 2.0 · GenEvalGenEval overall: 0.73 -> 0.72Hurt
train high-res stage after low-res stage (ablation)Lumina-Image 2.0 · DPGDPG overall: 84.5 -> 85.7Improved
add CFG-Renorm and CFG-Trunc (ablation)Lumina-Image 2.0 · 1024 resolution samplingsampling time and quality: over a 20% accelerationImproved
add Flow-DPM-Solver (ablation)Lumina-Image 2.0 · 1024 resolution samplingsampling time and sample qualityMixed
add TeaCache (ablation)Lumina-Image 2.0 · 1024 resolution samplingspeed and image qualityMixed
use longer, more precise UniCap captions instead of short Florence captions (ablation)Lumina-Image 2.0 · training lossconvergence speedImproved
replace cross-attention with joint self-attention (Unified Next-DiT) plus UniCap and more dataLumina-Next · DPGDPG overall: 75.66 -> 87.20Improved

Later papers that compared with this method

2 later accepted papers report Lumina-Image 2.0 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy